Multiple-valued bent functions are functions with highest nonlinearity which makes them interesting for multiple-valued cryptography. Since the general structure of bent functions is still unknown, methods for construction of bent functions are often based on some deterministic criteria. For practical applications, it is often necessary to be able to construct a bent function that does not belong to any specific class of functions. Thus, the criteria for constructions are combined with exhaustive search over all possible functions which can be very CPU time consuming. A solution is to restrict the search space by some conditions that should be satisfied by the produced bent functions. In this paper, we proposed the construction method based on spectral subsets of multiple-valued bent functions satisfying certain appropriately formulated restrictions in Galois field (GF) and Reed-Muller-Fourier (RMF) domains. Experimental results show that the proposed method efficiently constructs ternary and quaternary bent functions by using these restrictions.

Blockchain-based voting, including liquid voting, has been extensively studied in recent years. However, it remains challenging to implement liquid voting on blockchain using Ethereum smart contract. The challenge comes from the gas limit, which is that the number of instructions for processing a ballot cannot exceed a certain amount. This restricts the application scenario with respect to algorithms whose time complexity is linear to the number of voters, i.e., O(n). As the blockchain technology can well share and reuse the resources, we study a model of liquid voting on blockchain and propose a fast algorithm, named Flash, to eliminate the restriction. The key idea behind our algorithm is to shift some on-chain process to off-chain. In detail, we first construct a Merkle tree off-chain which contains all voters' properties. Second, we use Merkle proof and interval tree to process each ballot with O(log n) on-chain time complexity. Theoretically, the algorithm can support up to 21000 voters with respect to the current gas limit on Ethereum. Experimentally, the result implies that the consumed gas fee remains at a very low level when the number of voters increases. This means our algorithm makes liquid voting on blockchain practical even for massive voters.

Accurate and automatic quantitative cephalometry analysis is of great importance in orthodontics. The fundamental step for cephalometry analysis is to annotate anatomic-interested landmarks on X-ray images. Computer-aided automatic method remains to be an open topic nowadays. In this paper, we propose an efficient deep learning-based coarse-to-fine approach to realize accurate landmark detection. In the coarse detection step, we train a deep learning-based deformable transformation model by using training samples. We register test images to the reference image (one training image) using the trained model to predict coarse landmarks' locations on test images. Thus, regions of interest (ROIs) which include landmarks can be located. In the fine detection step, we utilize trained deep convolutional neural networks (CNNs), to detect landmarks in ROI patches. For each landmark, there is one corresponding neural network, which directly does regression to the landmark's coordinates. The fine step can be considered as a refinement or fine-tuning step based on the coarse detection step. We validated the proposed method on public dataset from 2015 International Symposium on Biomedical Imaging (ISBI) grand challenge. Compared with the state-of-the-art method, we not only achieved the comparable detection accuracy (the mean radial error is about 1.0-1.6mm), but also largely shortened the computation time (4 seconds per image).

In this paper, we focus on developing efficient multi-configuration selection mechanisms by exploiting the spatial degrees of freedom (DoF), and leveraging the simple design benefits of spatial modulation (SM). Notably, the SM technique, as well as its variants, faces the following critical challenges: (i) the performance degradation and difficulty in improving the system performance for higher-level QAM constellations, and (ii) the vast complexity cost in precoder designs particularly for the increasing system dimension and amplitude-phase modulation (APM) constellation dimension. Given this situation, we first investigate two independent modulation domains, i.e., the original signal- and spatial-constellations. By exploiting the analog shift weighting and the virtual spatial signature technologies, we introduce the signature spatial modulation (SSM) concept, which is capable of guaranteing superior trade-offs among spectral- and cost-efficiencies, and system bit error rate (BER) performance. Besides, we develop an analog beamforming for SSM by solving the introduced unconstrained Lagrange dual function minimization problem. Numerical results manifest the performance gain brought by our developed analog beamforming for SSM.

Speech recognition is a technique that recognizes words and sentences in audio form and converts them into text sentences. Currently, with the advancement of deep learning technologies, speech recognition has achieved very satisfactory results close to human abilities. However, there are still limitations in identification results such as lack of punctuation, capitalization, and standardized numerical data. Vietnamese also contains local words, homonyms, etc, which make it difficult to read and understand the identification results for users as well as to perform the next tasks in Natural Language Processing (NLP). In this paper, we propose to combine the transformer decoder with conditional random field (CRF) to restore punctuation and capitalization for the Vietnamese automatic speech recognition (ASR) output. By chunking input sentences and merging output sequences, it is possible to handle longer strings with greater accuracy. Experiments show that the method proposed in the Vietnamese post-speech recognition dataset delivers the best results.

Gait recognition distinguishes one individual from others according to the natural patterns of human gaits. Gait recognition is a challenging signal processing technology for biometric identification due to the ambiguity of contours and the complex feature extraction procedure. In this work, we proposed a new model - the convolutional neural network (CNN) joint attention mechanism (CJAM) - to classify the gait sequences and conduct person identification using the CASIA-A and CASIA-B gait datasets. The CNN model has the ability to extract gait features, and the attention mechanism continuously focuses on the most discriminative area to achieve person identification. We present a comprehensive transformation from gait image preprocessing to final identification. The results from 12 experiments show that the new attention model leads to a lower error rate than others. The CJAM model improved the 3D-CNN, CNN-LSTM (long short-term memory), and the simple CNN by 8.44%, 2.94% and 1.45%, respectively.

Aiming at the problem that traditional text-level sentiment analysis methods usually ignore the emotional tendency corresponding to the object or attribute. In this paper, a novel two-stage fine-grained text-level sentiment analysis model based on syntactic rule matching and deep semantics is proposed. Based on analyzing the characteristics and difficulties of fine-grained sentiment analysis, a two-stage fine-grained sentiment analysis algorithm framework is constructed. In the first stage, the objects and its corresponding opinions are extracted based on syntactic rules matching to obtain preliminary objects and opinions. The second stage based on deep semantic network to extract more accurate objects and opinions. Aiming at the problem that the extraction result contains multiple objects and opinions to be matched, an object-opinion matching algorithm based on the minimum lexical separation distance is proposed to achieve accurate pairwise matching. Finally, the proposed algorithm is evaluated on several public datasets to demonstrate its practicality and effectiveness.

Recently, automated recognition and analysis of human emotion has attracted increasing attention from multidisciplinary communities. However, it is challenging to utilize the emotional information simultaneously from multiple modalities. Previous studies have explored different fusion methods, but they mainly focused on either inter-modality interaction or intra-modality interaction. In this letter, we propose a novel two-stage fusion strategy named modality attention flow (MAF) to model the intra- and inter-modality interactions simultaneously in a unified end-to-end framework. Experimental results show that the proposed approach outperforms the widely used late fusion methods, and achieves even better performance when the number of stacked MAF blocks increases.

Video inpainting is a task of filling missing regions in videos. In this task, it is important to efficiently use information from other frames and generate plausible results with sufficient temporal consistency. In this paper, we present a video inpainting method jointly using affine transformation and deformable convolutions for frame alignment. The former is responsible for frame-scale rough alignment and the latter performs pixel-level fine alignment. Our model does not depend on 3D convolutions, which limits the temporal window, or troublesome flow estimation. The proposed method achieves improved object removal results and better PSNR and SSIM values compared with previous learning-based methods.

Robustness of complex networks is an essential subject for improving their performance when vertices or links are removed due to potential threats. In recent years, significant advancements have been achieved in this field by many researchers. In this paper we show an overview from a novel statistic perspective. We present a brief review about complex networks at first including 2 primary network models, 12 popular attack strategies and the most convincing network robustness metrics. Then, we focus on the correlations of 12 attack strategies with each other, and the difference of the correlations from one network model to the other. We are also curious about the robustness of networks when vertices are removed according to different attack strategies and the difference of robustness from one network model to the other. Our aim is to observe the correlation mechanism of centralities for distinct network models, and compare the network robustness when different centralities are applied as attacking directors to distinct network models. What inspires us is that maybe we can find a paradigm that combines several high-destructive attack strategies to find the optimal strategy based on the deep learning framework.

6DoF pose estimation from a monocular RGB image is a challenging but fundamental task. The methods based on unit direction vector-field representation and Hough voting strategy achieved state-of-the-art performance. Nevertheless, they apply the smooth l1 loss to learn the two elements of the unit vector separately, resulting in which is not taken into account that the prior distance between the pixel and the keypoint. While the positioning error is significantly affected by the prior distance. In this work, we propose a Prior Distance Augmented Loss (PDAL) to exploit the prior distance for more accurate vector-field representation. Furthermore, we propose a lightweight channel-level attention module for adaptive feature fusion. Embedding this Adaptive Fusion Attention Module (AFAM) into the U-Net, we build an Attention Voting Network to further improve the performance of our method. We conduct extensive experiments to demonstrate the effectiveness and performance improvement of our methods on the LINEMOD, OCCLUSION and YCB-Video datasets. Our experiments show that the proposed methods bring significant performance gains and outperform state-of-the-art RGB-based methods without any post-refinement.

The current approaches to semantic role classification usually first define a representation vector for a candidate role and feed the vector into a deep neural network to perform classification. The representation vector contains some lexicalization features like word embeddings, lemmar embeddings. From linguistics, the semantic role frame of a sentence is a joint structure with strong dependencies between arguments which is not considered in current deep SRL systems. Therefore, this paper proposes a global deep reranking model to exploit these strong dependencies. The evaluation experiments on the CoNLL 2009 shared tasks show that our system can outperforms a strong local system significantly that does not consider role dependency relations.

Reducing power consumption is crucial for edge devices using convolutional neural network (CNN). The zero-skipping approach for CNNs is a processing technique widely known for its relatively low power consumption and high speed. This approach stops multiplication and accumulation (MAC) when the multiplication results of the input data and weight are zero. However, this technique requires large logic circuits with around 5% overhead, and the average rate of MAC stopping is approximately 30%. In this paper, we propose a precise zero-skipping method that uses input data and simple logic circuits to stop multipliers and accumulators precisely. We also propose an active data-skipping method to further reduce power consumption by slightly degrading recognition accuracy. In this method, each multiplier and accumulator are stopped by using small values (e.g., 1, 2) as input. We implemented single shot multi-box detector 500 (SSD500) network model on a Xilinx ZU9 and applied our proposed techniques. We verified that operations were stopped at a rate of 49.1%, recognition accuracy was degraded by 0.29%, power consumption was reduced from 9.2 to 4.4 W (-52.3%), and circuit overhead was reduced from 5.1 to 2.7% (-45.9%). The proposed techniques were determined to be effective for lowering the power consumption of CNN-based edge devices such as FPGA.

In recent years, single face image super-resolution (SR) using deep neural networks have been well developed. However, most of the face images captured by the camera in a real scene are from different views of the same person, and the existing traditional multi-frame image SR requires alignment between images. Due to multi-view face images contain texture information from different views, which can be used as effective prior information, how to use this prior information from multi-views to reconstruct frontal face images is challenging. In order to effectively solve the above problems, we propose a novel face SR network based on multi-view face images, which focus on obtaining more texture information from multi-view face images to help the reconstruction of frontal face images. And in this network, we also propose a texture attention mechanism to transfer high-precision texture compensation information to the frontal face image to obtain better visual effects. We conduct subjective and objective evaluations, and the experimental results show the great potential of using multi-view face images SR. The comparison with other state-of-the-art deep learning SR methods proves that the proposed method has excellent performance.

This paper introduces a method to estimate latent traffic from its origin to destination from the link packet loss rate and traffic volume. In addition, we propose a method for the joint optimization of routing and link provisioning based on the estimated latent traffic. Observed traffic could deviate from the original traffic demand and become latent when the traffic passes through congested links because of changes in user behavioral and/or applications as a result of degraded quality of experience (QoE). The latent traffic is actualized by improving congested link capacity. When link provisioning is based on observed traffic, actual traffic might cause new congestion at other links. Thus, network providers need to estimate the origin-destination (OD) original traffic demand for network planning. Although the estimation of original traffic has been well studied, the estimation was only applicable for links. In this paper, we propose a method to estimate latent OD traffic by combining and expanding techniques. The method consists of three steps. The first step is to estimate the actual OD traffic and loss rate from the actual traffic and packet loss rate of the links. The second step is to estimate the latent traffic demand. Finally, using this estimated demand, the link capacity and routing matrix are optimized. We evaluate our method by simulation and confirm that congestion could be avoided by capacity provisioning based on estimated latent traffic, while provisioning based on observed traffic retains the congestion. The combined method can avoid congestion with an increment of 23% compared with capacity provisioning only. We also evaluated our method's adaptability, i.e., the ability to estimate the required parameter for the estimations using fewer given values, but values obtained in the environment.

Wireless Mesh Networks (WMNs) are often designed on IEEE 802.11 standards and are being widely studied due to their adaptability in practical network scenarios, where the overall performance has been improved by the use of the Multi-Radio and Multi-Channel (MRMC) configuration. However, because of the limitation on the number of available orthogonal channels and radios on each router, the network still suffers from low throughput due to packet collisions. Many studies have demonstrated that the optimized channel assignment to radio interfaces so as to avoid interference among wireless links is an effective solution. However, no existing channel assignment scheme can achieve hidden-terminal-free transmission and thus avoid communication performance degradation given the limited number of orthogonal channels. In this paper, we propose a new static channel assignment scheme CASCA (CSMA-aware Static Channel Assignment) based on a Partial MAX-SAT formulation of the channel assignment problem that incorporates a CSMA-aware interference model. The evaluation results show that CASCA achieves hidden-terminal-freedom in both grid and random topology networks with 3-4 orthogonal channels with preservation of network connectivity. In addition, the network simulation results show that CASCA presents good communication performance with low MAC-layer collision rate.

This paper proposes a pulse-width modulated (PWM) signaling[1] to send clock and data over a pair of channels for in-vehicle network where a closed chain of point-to-point (P2P) interconnection between electronic control units (ECU) has been established. To improve detection speed and margin of proposed receiver, we also proposed a novel clock and data recovery (CDR) scheme with 0.5 unit-interval (UI) tuning range and a PWM generator utilizing 10 equally-spaced phases. The feasibility of proposed system has been proved by successfully detecting 1.25 Gb/s data delivered via 3 ECUs and inter-channels in 180 nm CMOS technology. Compared to previous study, the proposed system achieved better efficiency in terms of power, cost, and reliability.

This paper proposes two high-fidelity and computationally efficient neural voice conversion (VC) methods based on a direct waveform modification using spectral differentials. The conventional spectral-differential VC method with a minimum-phase filter achieves high-quality conversion for narrow-band (16 kHz-sampled) VC but requires heavy computational cost in filtering. This is because the minimum phase obtained using a fixed lifter of the Hilbert transform often results in a long-tap filter. Furthermore, when we extend the method to full-band (48 kHz-sampled) VC, the computational cost is heavy due to increased sampling points, and the converted-speech quality degrades due to large fluctuations in the high-frequency band. To construct a short-tap filter, we propose a lifter-training method for data-driven phase reconstruction that trains a lifter of the Hilbert transform by taking into account filter truncation. We also propose a frequency-band-wise modeling method based on sub-band multi-rate signal processing (sub-band modeling method) for full-band VC. It enhances the computational efficiency by reducing sampling points of signals converted with filtering and improves converted-speech quality by modeling only the low-frequency band. We conducted several objective and subjective evaluations to investigate the effectiveness of the proposed methods through implementation of the real-time, online, full-band VC system we developed, which is based on the proposed methods. The results indicate that 1) the proposed lifter-training method for narrow-band VC can shorten the tap length to 1/16 without degrading the converted-speech quality, and 2) the proposed sub-band modeling method for full-band VC can improve the converted-speech quality while reducing the computational cost, and 3) our real-time, online, full-band VC system can convert 48 kHz-sampled speech in real time attaining the converted speech with a 3.6 out of 5.0 mean opinion score of naturalness.

In this paper, a deep learning-based secret key generation scheme is proposed for FDD multiple-input and multiple-output (MIMO) systems. We built an encoder-decoder based convolutional neural network to characterize the wireless environment to learn the mapping relationship between the uplink and downlink channel. The designed neural network can accurately predict the downlink channel state information based on the estimated uplink channel state information without any information feedback. Random secret keys can be generated from downlink channel responses predicted by the neural network. Simulation results show that deep learning based SKG scheme can achieve significant performance improvement in terms of the key agreement ratio and achievable secret key rate.

Millimeter wave provides high data rates for Vehicle-to-Everything (V2X) communications. This paper motivates millimeter wave to support automated driving and begins by explaining V2X use cases that support automated driving with references to several standardization bodies. The paper gives a classification of existing V2X standards: IEEE802.11p and LTE V2X, along with the status of their commercial deployment. Then, the paper provides a detailed assessment on how millimeter wave V2X enables the use case of cooperative perception. The explanations provide detailed rate calculations for this use case and show that millimeter wave is the only technology able to achieve the requirements. Furthermore, specific challenges related to millimeter wave for V2X are described, including coverage enhancement and beam alignment. The paper concludes with some results from three studies, i.e. IEEE802.11ad (WiGig) based V2X, extension of 5G NR (New Radio) toward mmWave V2X, and prototypes of intelligent street with mmWave V2X.